fev-bench / tables /pairwise_WAPE.csv
shchuro's picture
Add tables
18a3564
raw
history blame
10.7 kB
model_1,model_2,win_rate,win_rate_lower,win_rate_upper,skill_score,skill_score_lower,skill_score_upper
TimesFM-2.5,TimesFM-2.5,0.5,0.5,0.5,0.0,0.0,0.0
TimesFM-2.5,TiRex,0.505,0.42,0.6,0.004,-0.013,0.021
TimesFM-2.5,Toto-1.0,0.54,0.455,0.635,0.034,0.008,0.062
TimesFM-2.5,TabPFN-TS,0.63,0.53,0.72,0.007,-0.04,0.054
TimesFM-2.5,Moirai-2.0,0.71,0.625,0.79,0.046,0.021,0.071
TimesFM-2.5,Chronos-Bolt,0.74,0.66,0.82,0.058,0.036,0.081
TimesFM-2.5,Sundial-Base,0.835,0.76,0.905,0.09,0.054,0.127
TimesFM-2.5,Stat. Ensemble,0.84,0.76,0.91,0.196,0.146,0.244
TimesFM-2.5,AutoARIMA,0.91,0.85,0.97,0.237,0.191,0.286
TimesFM-2.5,AutoETS,0.85,0.78,0.91,0.308,0.239,0.377
TimesFM-2.5,AutoTheta,0.92,0.86,0.97,0.232,0.188,0.277
TimesFM-2.5,Naive,0.93,0.87,0.98,0.376,0.322,0.43
TimesFM-2.5,Seasonal Naive,0.95,0.9,0.99,0.338,0.294,0.388
TimesFM-2.5,Drift,0.92,0.86,0.97,0.391,0.338,0.446
TiRex,TimesFM-2.5,0.495,0.4,0.58,-0.004,-0.021,0.013
TiRex,TiRex,0.5,0.5,0.5,0.0,0.0,0.0
TiRex,Toto-1.0,0.625,0.53,0.72,0.03,0.007,0.051
TiRex,TabPFN-TS,0.65,0.56,0.74,0.003,-0.045,0.052
TiRex,Moirai-2.0,0.695,0.615,0.79,0.042,0.023,0.065
TiRex,Chronos-Bolt,0.745,0.66,0.83,0.054,0.032,0.077
TiRex,Sundial-Base,0.775,0.695,0.85,0.087,0.048,0.126
TiRex,Stat. Ensemble,0.82,0.73,0.89,0.193,0.146,0.242
TiRex,AutoARIMA,0.88,0.81,0.94,0.234,0.189,0.282
TiRex,AutoETS,0.84,0.76,0.91,0.306,0.233,0.374
TiRex,AutoTheta,0.93,0.88,0.98,0.229,0.187,0.272
TiRex,Naive,0.93,0.88,0.98,0.374,0.321,0.429
TiRex,Seasonal Naive,0.95,0.9,0.99,0.336,0.29,0.384
TiRex,Drift,0.91,0.85,0.96,0.388,0.335,0.443
Toto-1.0,TimesFM-2.5,0.46,0.365,0.545,-0.035,-0.066,-0.008
Toto-1.0,TiRex,0.375,0.28,0.47,-0.031,-0.054,-0.007
Toto-1.0,Toto-1.0,0.5,0.5,0.5,0.0,0.0,0.0
Toto-1.0,TabPFN-TS,0.56,0.47,0.65,-0.028,-0.083,0.024
Toto-1.0,Moirai-2.0,0.6,0.5,0.69,0.012,-0.012,0.036
Toto-1.0,Chronos-Bolt,0.6,0.505,0.685,0.024,-0.004,0.052
Toto-1.0,Sundial-Base,0.665,0.575,0.75,0.058,0.011,0.103
Toto-1.0,Stat. Ensemble,0.69,0.59,0.78,0.168,0.115,0.219
Toto-1.0,AutoARIMA,0.82,0.74,0.89,0.21,0.157,0.261
Toto-1.0,AutoETS,0.77,0.68,0.84,0.284,0.208,0.353
Toto-1.0,AutoTheta,0.87,0.8,0.93,0.205,0.158,0.252
Toto-1.0,Naive,0.91,0.85,0.96,0.354,0.296,0.408
Toto-1.0,Seasonal Naive,0.92,0.86,0.97,0.315,0.266,0.365
Toto-1.0,Drift,0.9,0.83,0.96,0.369,0.315,0.424
TabPFN-TS,TimesFM-2.5,0.37,0.28,0.47,-0.007,-0.057,0.038
TabPFN-TS,TiRex,0.35,0.26,0.44,-0.003,-0.055,0.043
TabPFN-TS,Toto-1.0,0.44,0.35,0.53,0.027,-0.024,0.076
TabPFN-TS,TabPFN-TS,0.5,0.5,0.5,0.0,0.0,0.0
TabPFN-TS,Moirai-2.0,0.52,0.42,0.62,0.039,-0.012,0.085
TabPFN-TS,Chronos-Bolt,0.53,0.44,0.62,0.051,0.006,0.094
TabPFN-TS,Sundial-Base,0.66,0.56,0.75,0.084,0.041,0.126
TabPFN-TS,Stat. Ensemble,0.775,0.695,0.855,0.19,0.134,0.242
TabPFN-TS,AutoARIMA,0.83,0.76,0.9,0.232,0.178,0.283
TabPFN-TS,AutoETS,0.77,0.69,0.85,0.303,0.23,0.382
TabPFN-TS,AutoTheta,0.84,0.76,0.9,0.227,0.18,0.277
TabPFN-TS,Naive,0.91,0.85,0.96,0.372,0.316,0.432
TabPFN-TS,Seasonal Naive,0.94,0.89,0.98,0.334,0.29,0.379
TabPFN-TS,Drift,0.89,0.83,0.95,0.386,0.328,0.447
Moirai-2.0,TimesFM-2.5,0.29,0.21,0.375,-0.048,-0.077,-0.021
Moirai-2.0,TiRex,0.305,0.21,0.385,-0.044,-0.069,-0.023
Moirai-2.0,Toto-1.0,0.4,0.31,0.5,-0.012,-0.038,0.012
Moirai-2.0,TabPFN-TS,0.48,0.38,0.58,-0.041,-0.093,0.012
Moirai-2.0,Moirai-2.0,0.5,0.5,0.5,0.0,0.0,0.0
Moirai-2.0,Chronos-Bolt,0.56,0.48,0.645,0.013,-0.011,0.036
Moirai-2.0,Sundial-Base,0.665,0.57,0.76,0.047,0.005,0.087
Moirai-2.0,Stat. Ensemble,0.74,0.65,0.82,0.157,0.105,0.208
Moirai-2.0,AutoARIMA,0.83,0.75,0.9,0.2,0.148,0.254
Moirai-2.0,AutoETS,0.77,0.68,0.85,0.275,0.196,0.35
Moirai-2.0,AutoTheta,0.88,0.81,0.94,0.196,0.147,0.243
Moirai-2.0,Naive,0.87,0.8,0.93,0.346,0.29,0.403
Moirai-2.0,Seasonal Naive,0.87,0.8,0.93,0.307,0.258,0.357
Moirai-2.0,Drift,0.87,0.8,0.93,0.361,0.303,0.417
Chronos-Bolt,TimesFM-2.5,0.26,0.18,0.34,-0.061,-0.088,-0.037
Chronos-Bolt,TiRex,0.255,0.17,0.34,-0.057,-0.083,-0.033
Chronos-Bolt,Toto-1.0,0.4,0.315,0.495,-0.025,-0.055,0.004
Chronos-Bolt,TabPFN-TS,0.47,0.38,0.56,-0.054,-0.104,-0.006
Chronos-Bolt,Moirai-2.0,0.44,0.355,0.52,-0.013,-0.038,0.011
Chronos-Bolt,Chronos-Bolt,0.5,0.5,0.5,0.0,0.0,0.0
Chronos-Bolt,Sundial-Base,0.635,0.54,0.73,0.034,-0.006,0.071
Chronos-Bolt,Stat. Ensemble,0.74,0.64,0.82,0.147,0.096,0.198
Chronos-Bolt,AutoARIMA,0.85,0.77,0.92,0.19,0.137,0.242
Chronos-Bolt,AutoETS,0.77,0.68,0.85,0.266,0.19,0.341
Chronos-Bolt,AutoTheta,0.92,0.87,0.97,0.185,0.139,0.232
Chronos-Bolt,Naive,0.89,0.83,0.95,0.338,0.28,0.394
Chronos-Bolt,Seasonal Naive,0.91,0.85,0.96,0.298,0.252,0.345
Chronos-Bolt,Drift,0.9,0.84,0.95,0.353,0.296,0.41
Sundial-Base,TimesFM-2.5,0.165,0.095,0.24,-0.099,-0.145,-0.057
Sundial-Base,TiRex,0.225,0.15,0.305,-0.095,-0.144,-0.05
Sundial-Base,Toto-1.0,0.335,0.25,0.425,-0.062,-0.115,-0.012
Sundial-Base,TabPFN-TS,0.34,0.25,0.44,-0.092,-0.144,-0.042
Sundial-Base,Moirai-2.0,0.335,0.24,0.43,-0.049,-0.095,-0.005
Sundial-Base,Chronos-Bolt,0.365,0.27,0.46,-0.036,-0.076,0.006
Sundial-Base,Sundial-Base,0.5,0.5,0.5,0.0,0.0,0.0
Sundial-Base,Stat. Ensemble,0.64,0.54,0.73,0.116,0.05,0.174
Sundial-Base,AutoARIMA,0.76,0.67,0.84,0.161,0.097,0.218
Sundial-Base,AutoETS,0.68,0.58,0.77,0.24,0.149,0.317
Sundial-Base,AutoTheta,0.74,0.64,0.82,0.156,0.099,0.206
Sundial-Base,Naive,0.82,0.74,0.89,0.315,0.248,0.38
Sundial-Base,Seasonal Naive,0.88,0.81,0.94,0.273,0.225,0.319
Sundial-Base,Drift,0.81,0.73,0.88,0.33,0.261,0.398
Stat. Ensemble,TimesFM-2.5,0.16,0.09,0.24,-0.244,-0.323,-0.171
Stat. Ensemble,TiRex,0.18,0.11,0.27,-0.239,-0.319,-0.171
Stat. Ensemble,Toto-1.0,0.31,0.22,0.41,-0.201,-0.28,-0.13
Stat. Ensemble,TabPFN-TS,0.225,0.145,0.305,-0.235,-0.32,-0.155
Stat. Ensemble,Moirai-2.0,0.26,0.18,0.35,-0.187,-0.263,-0.117
Stat. Ensemble,Chronos-Bolt,0.26,0.18,0.36,-0.172,-0.246,-0.107
Stat. Ensemble,Sundial-Base,0.36,0.27,0.46,-0.132,-0.211,-0.052
Stat. Ensemble,Stat. Ensemble,0.5,0.5,0.5,0.0,0.0,0.0
Stat. Ensemble,AutoARIMA,0.65,0.56,0.74,0.051,0.02,0.086
Stat. Ensemble,AutoETS,0.785,0.7,0.86,0.14,0.071,0.209
Stat. Ensemble,AutoTheta,0.81,0.73,0.88,0.045,0.009,0.078
Stat. Ensemble,Naive,0.84,0.77,0.91,0.224,0.169,0.277
Stat. Ensemble,Seasonal Naive,0.835,0.77,0.9,0.177,0.138,0.221
Stat. Ensemble,Drift,0.86,0.79,0.92,0.242,0.192,0.293
AutoARIMA,TimesFM-2.5,0.09,0.03,0.15,-0.31,-0.401,-0.236
AutoARIMA,TiRex,0.12,0.06,0.19,-0.305,-0.393,-0.233
AutoARIMA,Toto-1.0,0.18,0.11,0.26,-0.266,-0.353,-0.187
AutoARIMA,TabPFN-TS,0.17,0.1,0.24,-0.301,-0.395,-0.217
AutoARIMA,Moirai-2.0,0.17,0.1,0.25,-0.251,-0.341,-0.173
AutoARIMA,Chronos-Bolt,0.15,0.08,0.23,-0.235,-0.319,-0.159
AutoARIMA,Sundial-Base,0.24,0.16,0.33,-0.192,-0.278,-0.107
AutoARIMA,Stat. Ensemble,0.35,0.26,0.44,-0.054,-0.095,-0.02
AutoARIMA,AutoARIMA,0.5,0.5,0.5,0.0,0.0,0.0
AutoARIMA,AutoETS,0.555,0.46,0.655,0.093,0.015,0.175
AutoARIMA,AutoTheta,0.52,0.42,0.62,-0.006,-0.057,0.039
AutoARIMA,Naive,0.72,0.63,0.8,0.183,0.118,0.242
AutoARIMA,Seasonal Naive,0.8,0.735,0.875,0.133,0.09,0.178
AutoARIMA,Drift,0.75,0.65,0.83,0.201,0.14,0.261
AutoETS,TimesFM-2.5,0.15,0.09,0.22,-0.446,-0.605,-0.314
AutoETS,TiRex,0.16,0.09,0.24,-0.44,-0.598,-0.303
AutoETS,Toto-1.0,0.23,0.16,0.32,-0.396,-0.547,-0.263
AutoETS,TabPFN-TS,0.23,0.15,0.31,-0.436,-0.617,-0.299
AutoETS,Moirai-2.0,0.23,0.15,0.32,-0.38,-0.538,-0.243
AutoETS,Chronos-Bolt,0.23,0.15,0.32,-0.362,-0.518,-0.235
AutoETS,Sundial-Base,0.32,0.23,0.42,-0.315,-0.464,-0.175
AutoETS,Stat. Ensemble,0.215,0.14,0.3,-0.162,-0.264,-0.077
AutoETS,AutoARIMA,0.445,0.345,0.54,-0.103,-0.212,-0.015
AutoETS,AutoETS,0.5,0.5,0.5,0.0,0.0,0.0
AutoETS,AutoTheta,0.47,0.37,0.56,-0.11,-0.214,-0.027
AutoETS,Naive,0.62,0.53,0.72,0.098,0.018,0.177
AutoETS,Seasonal Naive,0.685,0.585,0.775,0.043,-0.061,0.128
AutoETS,Drift,0.74,0.66,0.82,0.119,0.042,0.194
AutoTheta,TimesFM-2.5,0.08,0.03,0.14,-0.303,-0.383,-0.231
AutoTheta,TiRex,0.07,0.02,0.12,-0.297,-0.374,-0.23
AutoTheta,Toto-1.0,0.13,0.07,0.2,-0.258,-0.337,-0.188
AutoTheta,TabPFN-TS,0.16,0.1,0.24,-0.294,-0.383,-0.22
AutoTheta,Moirai-2.0,0.12,0.06,0.19,-0.243,-0.32,-0.172
AutoTheta,Chronos-Bolt,0.08,0.03,0.13,-0.227,-0.302,-0.161
AutoTheta,Sundial-Base,0.26,0.18,0.36,-0.185,-0.26,-0.11
AutoTheta,Stat. Ensemble,0.19,0.12,0.27,-0.047,-0.085,-0.009
AutoTheta,AutoARIMA,0.48,0.38,0.58,0.006,-0.041,0.054
AutoTheta,AutoETS,0.53,0.44,0.63,0.099,0.026,0.177
AutoTheta,AutoTheta,0.5,0.5,0.5,0.0,0.0,0.0
AutoTheta,Naive,0.76,0.68,0.84,0.188,0.138,0.239
AutoTheta,Seasonal Naive,0.78,0.69,0.86,0.138,0.099,0.18
AutoTheta,Drift,0.78,0.7,0.86,0.206,0.158,0.26
Naive,TimesFM-2.5,0.07,0.02,0.13,-0.603,-0.754,-0.476
Naive,TiRex,0.07,0.02,0.12,-0.597,-0.75,-0.473
Naive,Toto-1.0,0.09,0.04,0.15,-0.549,-0.689,-0.421
Naive,TabPFN-TS,0.09,0.04,0.15,-0.592,-0.761,-0.461
Naive,Moirai-2.0,0.13,0.07,0.2,-0.53,-0.674,-0.408
Naive,Chronos-Bolt,0.11,0.05,0.17,-0.511,-0.649,-0.39
Naive,Sundial-Base,0.18,0.11,0.26,-0.459,-0.613,-0.331
Naive,Stat. Ensemble,0.16,0.09,0.23,-0.289,-0.383,-0.203
Naive,AutoARIMA,0.28,0.2,0.37,-0.223,-0.319,-0.134
Naive,AutoETS,0.38,0.28,0.47,-0.109,-0.215,-0.018
Naive,AutoTheta,0.24,0.16,0.32,-0.231,-0.314,-0.161
Naive,Naive,0.5,0.5,0.5,0.0,0.0,0.0
Naive,Seasonal Naive,0.475,0.39,0.565,-0.061,-0.146,0.017
Naive,Drift,0.84,0.77,0.91,0.023,-0.005,0.048
Seasonal Naive,TimesFM-2.5,0.05,0.01,0.1,-0.511,-0.633,-0.417
Seasonal Naive,TiRex,0.05,0.01,0.1,-0.505,-0.623,-0.408
Seasonal Naive,Toto-1.0,0.08,0.03,0.14,-0.46,-0.575,-0.362
Seasonal Naive,TabPFN-TS,0.06,0.02,0.11,-0.501,-0.61,-0.409
Seasonal Naive,Moirai-2.0,0.13,0.07,0.2,-0.442,-0.555,-0.347
Seasonal Naive,Chronos-Bolt,0.09,0.04,0.15,-0.424,-0.527,-0.336
Seasonal Naive,Sundial-Base,0.12,0.06,0.19,-0.375,-0.469,-0.29
Seasonal Naive,Stat. Ensemble,0.165,0.1,0.23,-0.215,-0.283,-0.161
Seasonal Naive,AutoARIMA,0.2,0.125,0.265,-0.153,-0.217,-0.099
Seasonal Naive,AutoETS,0.315,0.225,0.415,-0.045,-0.147,0.057
Seasonal Naive,AutoTheta,0.22,0.14,0.31,-0.16,-0.219,-0.11
Seasonal Naive,Naive,0.525,0.435,0.61,0.058,-0.017,0.127
Seasonal Naive,Seasonal Naive,0.5,0.5,0.5,0.0,0.0,0.0
Seasonal Naive,Drift,0.64,0.53,0.73,0.079,-0.001,0.153
Drift,TimesFM-2.5,0.08,0.03,0.14,-0.641,-0.804,-0.51
Drift,TiRex,0.09,0.04,0.15,-0.635,-0.796,-0.504
Drift,Toto-1.0,0.1,0.04,0.17,-0.585,-0.735,-0.459
Drift,TabPFN-TS,0.11,0.05,0.17,-0.63,-0.807,-0.488
Drift,Moirai-2.0,0.13,0.07,0.2,-0.566,-0.715,-0.435
Drift,Chronos-Bolt,0.1,0.05,0.16,-0.546,-0.695,-0.42
Drift,Sundial-Base,0.19,0.12,0.27,-0.493,-0.66,-0.354
Drift,Stat. Ensemble,0.14,0.08,0.21,-0.32,-0.415,-0.238
Drift,AutoARIMA,0.25,0.17,0.35,-0.252,-0.353,-0.163
Drift,AutoETS,0.26,0.18,0.34,-0.135,-0.24,-0.044
Drift,AutoTheta,0.22,0.14,0.3,-0.26,-0.351,-0.188
Drift,Naive,0.16,0.09,0.23,-0.023,-0.051,0.005
Drift,Seasonal Naive,0.36,0.27,0.47,-0.086,-0.181,0.001
Drift,Drift,0.5,0.5,0.5,0.0,0.0,0.0